Each statistical model presented below scores a target sequence window S for similarity, in terms of k-mer composition, to a training set of known CRMs from Drosophila (see supplementary file S1, Supplementary Material online), denoted by C.
The PS α score is the total score for a target across all 182 compounds over the ten models derived from the ten different partitions of the ChEMBL dataset.
B7 Unease at the U.N. NOW A TARGET -- As scores of world leaders converge on New York this week for the United Nations General Assembly, Osama bin Laden's latest message to the world has provoked new security concerns for the United Nations and its global workforce.
We perform this comparison because both SEA and our approach use active ligand set to represent target, and use 2D fingerprint based similarity to obtain the score of a target (The SEA approach can be considered as a data fusion scheme, where the score of a target is normalized by the size of its ligand set).
Given a query compound, its similarity score to a target is represented by a set of reference ligands is obtained by fusing the pairwise fingerprint-based molecular similarities.
De novo design, the branch of chemoinformatics addressing the in silico design of ligands from scratch, follows a similar approach typically focusing on a single objective, such as an interaction score to a target receptor or similarity to a known drug [1].
1. Estimate the enrichment score of a target gene set W, (12) s ¯ = 1 m ∑ i ∈ W s i.
The overall synthetic accessibility score of a target structure is calculated by summing the five weighted individual components.
It consists of associating a score to a target node of interest for a given network, that will quantify the effect of experimental data.
SEPPA [ 11] was another structure-based predictor, which produced a propensity score for a target residue by considering its adjacent residues' information.
